%0 Conference Proceedings %T Hierarchical Sketch Induction for Paraphrase Generation %A Hosking, Tom %A Tang, Hao %A Lapata, Mirella %Y Muresan, Smaranda %Y Nakov, Preslav %Y Villavicencio, Aline %S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) %D 2022 %8 May %I Association for Computational Linguistics %C Dublin, Ireland %F hosking-etal-2022-hierarchical %X We propose a generative model of paraphrase generation, that encourages syntactic diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings as a sequence of discrete latent variables that make iterative refinements of increasing granularity. This hierarchy of codes is learned through end-to-end training, and represents fine-to-coarse grained information about the input. We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time. Extensive experiments, including a human evaluation, confirm that HRQ-VAE learns a hierarchical representation of the input space, and generates paraphrases of higher quality than previous systems. %R 10.18653/v1/2022.acl-long.178 %U https://aclanthology.org/2022.acl-long.178 %U https://doi.org/10.18653/v1/2022.acl-long.178 %P 2489-2501